# Heygen v5 Digital Twin API

> Digitaler Zwilling von Avatar V mit 4k-Ausgabe, transparentem WebM, Hintergrund, Wasserzeichen und SRT-Untertiteln

Erstellt ein sprechendes Avatarvideo aus Text (`prompt` und `voice`) oder aus einer `audio_url` für Lippensynchronisation. Wähle ein benanntes `avatar`, einen `fit`-Modus mit contain oder cover sowie eine Auflösung von 720p, 1080p oder 4k. `output_format` kann mp4 oder webm sein; webm ist transparent. Zu den Optionen gehören Hintergrundkomposition, ein Wasserzeichen-Overlay und eine separate SRT-Untertiteldatei.

- Model id: `heygen/avatar5/digital-twin`
- Made by: HeyGen
- Category: Lipsync & Avatars
- Output: video
- Price per second of your input audio: $0.10 / second of input audio (cheapest run $0.10 (100 API credits))
- Run: `POST https://api.doitong.com/v1/run/heygen/avatar5/digital-twin`
- Quote: `POST https://api.doitong.com/v1/quote/heygen/avatar5/digital-twin`
- Docs page: https://doitong.com/de/developers/models/heygen/avatar5/digital-twin

## Pricing

Price: **$0.10 / second of input audio**. Price per second of your input audio: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $1.00 = 1000 API credits (10 s input audio × $0.10).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/heygen/avatar5/digital-twin` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `avatar` |  | string \| null | no | `Abigail Sofa Front` |  | Name zur Identifizierung eines für Avatar V geeigneten Avatars. |
| `prompt` |  | string \| null | no |  |  | Sprechtext für den Avatar; erforderlich, wenn `audio_url` fehlt. |
| `voice` |  | enum (string) \| null | no | `Warm Pro Narrator` | `Warm Pro Narrator`, `Chill Brian`, `Ivy`, `John Doe`, `Monika Sogam`, `Hope `, `Archer `, `Brittney`, `Patrick`, `David Castlemore`, `Michael C`, `Adam Stone `, `Juniper`, `Cassidy `, `Jessica Anne Bogart`, `Arabella`, `Andrew`, `Spuds Oxley `, `Grace Elder`, `Helen`, `Canyon Rivers`, `Derya - Lifelike - Excited 🤩`, `Mellow Marcus`, `Jack Sterling - Broadcaster 🎙️`, `Brenda - UGC - 1.mp4`, `Reid`, `Reagan`, `Terry`, `Jenny`, `Radio Rick`, `Denise`, `Tim in car - Excited 🤩`, `Iskander`, `Thompson`, `Delicate Daisy - Excited 🤩`, `Kingston`, `George UGC 1`, `Bold Blake`, `Jane`, `Expressive Evan`, `Marianne - IA`, `Aaron`, `Modern Recipe Host - Voice 1`, `Willow`, `Cute Chloe - Friendly 😊`, `Rafael`, `June - Lifelike`, `Crisp Chloe`, `Slick Simon`, `Nassim - Informative`, `Baritone Ben`, `Maxwell`, `Ellie Faye - Excited 🤩`, `Milani`, `Feisty Fiona - Excited 🤩`, `Professor Dean`, `Rose - UGC - 1.mp4`, `Shona`, `Hudson Wilder`, `Ann - IA`, `Alastair Kensington`, `Oxley`, `Christina`, `Andrew Rizz `, `Peyton`, `Gerardo - Outdoor`, `Chloe - Lifelike`, `Stephanie`, `Anthony - IA`, `Signal - Voice 1`, `Luca`, `Lisa - Voice 1`, `T.W.Tucker`, `Jack Sullivan - Serious 😐`, `Winter`, `Mireia - Lifelike`, `Georgia`, `Stella`, `Masha - Lifelike`, `Charming Charles - Friendly 😊`, `Serenity`, `Annie - Excited`, `Ralph`, `Bethany`, `Dominic`, `Mason Finn`, `Leena`, `Veteran Victor`, `Tamara`, `Nik Public`, `Calm Chloe`, `Sevik`, `Reilly`, `Raul`, `Imposing Ian`, `Relaxed Ray`, `Dexter - Professional`, `Relaxed Rick`, `Edwin`, `Rupert Blackwood`, `Ginny`, `Hope` | Auswahl der Avatarstimme nach Namen für Text-to-Speech; gilt nur ohne `audio_url`. |
| `audio_url` | `audio` | string (audio URL) \| null | no |  |  | Quelle für Lippensynchronisation als HTTP(S)-URL einer Audiodatei, die bei Vorhandensein Text-to-Speech ersetzt. In diesem Fall werden weder `prompt` noch `voice` verwendet. |
| `fit` |  | enum (string) | no | `cover` | `contain`, `cover` | Wählt den Bildausschnitt des Avatars: 'cover' füllt den Ausgabe-Frame, kann den Avatar jedoch beschneiden, während 'contain' den gesamten Avatar zeigt, aber Letterboxing hinzufügen kann. |
| `remove_background` |  | boolean | no | `false` |  | Hintergrundentfernung für den Avatar; nur für Avatare verfügbar, die Matting unterstützen. |
| `background` |  | object {type, value} \| null | no |  |  | Optional hinter dem Avatar platzierter Hintergrund, außer bei `output_format='webm'`: Transparente WebM-Ausgabe ignoriert diese Einstellung. |
| `background.type` |  | enum (string) | no | `color` | `color`, `image` | Hintergrundtyp: `color` gibt eine einfarbige hexadezimale Farbe an, `image` eine Bild-URL. |
| `background.value` |  | string | no | `#FFFFFF` |  | Hintergrundinhalt: eine hexadezimale Farbe, wenn der Typ `color` ist, oder eine HTTP(S)-URL, wenn der Typ `image` ist. |
| `watermark` |  | object {image_url, scale, opacity, placement} \| null | no |  |  | Optionales Bild als Wasserzeichen-Overlay im generierten Video. |
| `watermark.image_url` |  | string (image URL) | yes |  |  | HTTP(S)-URL des Wasserzeichenbilds zum Überlagern im Video. |
| `watermark.scale` |  | number \| null | no |  | ≤ 2, > 0 | Größe des Wasserzeichens relativ zum Video, größer als 0.0 und höchstens 2.0. |
| `watermark.opacity` |  | number \| null | no |  | 0 – 1 | Transparenz des Wasserzeichens: 0.0 ist vollständig transparent, 1.0 vollständig deckend. |
| `watermark.placement` |  | enum (string) \| null | no |  | `top-left`, `top-right`, `bottom-left`, `bottom-right` | Position des Wasserzeichens im Video. |
| `caption` |  | boolean | no | `false` |  | Steuert die Generierung einer separaten, zum Video gehörenden SRT-Untertiteldatei. |
| `output_format` |  | enum (string) | no | `mp4` | `mp4`, `webm` | Auswahl des Video-Containers; `webm` ermöglicht Transparenz durch automatische Hintergrundentfernung. In diesem Modus hat `background` keine Wirkung. |
| `resolution` |  | enum (string) | no | `720p` | `720p`, `1080p`, `4k` | Auflösungsvoreinstellung für die generierte Ausgabe. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `16:9`, `9:16`, `4:5`, `5:4`, `1:1`, `auto` | Auswahl des Video-Seitenverhältnisses: 'auto' weist HeyGen an, das Quellverhältnis zu erkennen und beizubehalten; falls dies nicht möglich ist, wird '16:9' verwendet. Explizite Verhältnisse sind '16:9', '9:16', '4:5', '5:4' und '1:1'. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Die Prüfung kann durch Setzen auf false gelockert werden, sofern der Aufrufer dazu berechtigt ist. |

File parameters (`audio`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/heygen/avatar5/digital-twin?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/heygen/avatar5/digital-twin?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/heygen/avatar5/digital-twin", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "heygen/avatar5/digital-twin",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "heygen/avatar5/digital-twin",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1000,
    "usd": "1.00",
    "charged": 1000,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "caption_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Von Avatar V erzeugte Videodatei. |
| `caption_file` | object {url, content_type, file_name, file_size} \| null | Bei `caption=True` erzeugte SRT-Untertiteldatei, sofern der Dienst eine bereitstellt. |

## Related models

- [Kling AI Avatar 2.0 Pro](https://doitong.com/developers/models/kling-video/ai-avatar/v2/pro.md) (`kling-video/ai-avatar/v2/pro`): $0.115 / second of input audio
- [Sync Lipsync 3](https://doitong.com/developers/models/sync-lipsync/v3.md) (`sync-lipsync/v3`): $8.00 / minute of output video
- [VEED Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0.md) (`veed/fabric-1.0`): from $0.08 / second of input audio
- [Heygen Lipsync - Precision](https://doitong.com/developers/models/heygen/v3/lipsync/precision.md) (`heygen/v3/lipsync/precision`): $0.10 / second of output video
- [Heygen Lipsync - Speed](https://doitong.com/developers/models/heygen/v3/lipsync/speed.md) (`heygen/v3/lipsync/speed`): $0.05 / second of output video
- [Heygen · Avatar3 · Digital Twin](https://doitong.com/developers/models/heygen/avatar3/digital-twin.md) (`heygen/avatar3/digital-twin`): $0.034 / second of input audio
- [Heygen · Avatar4 · Digital Twin](https://doitong.com/developers/models/heygen/avatar4/digital-twin.md) (`heygen/avatar4/digital-twin`): $0.10 / second of input audio
- [Heygen · Avatar4 · Image to Video](https://doitong.com/developers/models/heygen/avatar4/image-to-video.md) (`heygen/avatar4/image-to-video`): $0.10 / second of input audio

## Links

- HTML page: https://doitong.com/developers/models/heygen/avatar5/digital-twin
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=heygen/avatar5/digital-twin
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/heygen/avatar5/digital-twin